Merge tag 'v5.4.84' into v5.4-rt

This is the 5.4.84 stable release

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 4
-SUBLEVEL = 82
+SUBLEVEL = 84
 EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 
@@ -802,8 +802,11 @@ DEBUG_CFLAGS	+= -gsplit-dwarf
 else
 DEBUG_CFLAGS	+= -g
 endif
+ifneq ($(LLVM_IAS),1)
 KBUILD_AFLAGS	+= -Wa,-gdwarf-2
 endif
+endif
+
 ifdef CONFIG_DEBUG_INFO_DWARF4
 DEBUG_CFLAGS	+= -gdwarf-4
 endif

arch/arc/kernel/stacktrace.c

@@ -38,15 +38,15 @@
 
 #ifdef CONFIG_ARC_DW2_UNWIND
 
-static void seed_unwind_frame_info(struct task_struct *tsk,
-				   struct pt_regs *regs,
-				   struct unwind_frame_info *frame_info)
+static int
+seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs,
+		       struct unwind_frame_info *frame_info)
 {
 	/*
 	 * synchronous unwinding (e.g. dump_stack)
 	 *  - uses current values of SP and friends
 	 */
-	if (tsk == NULL && regs == NULL) {
+	if (regs == NULL && (tsk == NULL || tsk == current)) {
 		unsigned long fp, sp, blink, ret;
 		frame_info->task = current;
 
@@ -65,11 +65,15 @@ static void seed_unwind_frame_info(struct task_struct *tsk,
 		frame_info->call_frame = 0;
 	} else if (regs == NULL) {
 		/*
-		 * Asynchronous unwinding of sleeping task
-		 *  - Gets SP etc from task's pt_regs (saved bottom of kernel
-		 *    mode stack of task)
+		 * Asynchronous unwinding of a likely sleeping task
+		 *  - first ensure it is actually sleeping
+		 *  - if so, it will be in __switch_to, kernel mode SP of task
+		 *    is safe-kept and BLINK at a well known location in there
 		 */
 
+		if (tsk->state == TASK_RUNNING)
+			return -1;
+
 		frame_info->task = tsk;
 
 		frame_info->regs.r27 = TSK_K_FP(tsk);
@@ -103,6 +107,8 @@ static void seed_unwind_frame_info(struct task_struct *tsk,
 		frame_info->regs.r63 = regs->ret;
 		frame_info->call_frame = 0;
 	}
+
+	return 0;
 }
 
 #endif
@@ -116,7 +122,8 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 	unsigned int address;
 	struct unwind_frame_info frame_info;
 
-	seed_unwind_frame_info(tsk, regs, &frame_info);
+	if (seed_unwind_frame_info(tsk, regs, &frame_info))
+		return 0;
 
 	while (1) {
 		address = UNW_PC(&frame_info);

arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi

@@ -5,20 +5,20 @@
 	usb {
 		compatible = "simple-bus";
 		dma-ranges;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0x0 0x0 0x68500000 0x00400000>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges = <0x0 0x0 0x0 0x68500000 0x0 0x00400000>;
 
 		usbphy0: usb-phy@0 {
 			compatible = "brcm,sr-usb-combo-phy";
-			reg = <0x00000000 0x100>;
+			reg = <0x0 0x00000000 0x0 0x100>;
 			#phy-cells = <1>;
 			status = "disabled";
 		};
 
 		xhci0: usb@1000 {
 			compatible = "generic-xhci";
-			reg = <0x00001000 0x1000>;
+			reg = <0x0 0x00001000 0x0 0x1000>;
 			interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>;
 			phys = <&usbphy0 1>, <&usbphy0 0>;
 			phy-names = "phy0", "phy1";
@@ -28,7 +28,7 @@
 
 		bdc0: usb@2000 {
 			compatible = "brcm,bdc-v0.16";
-			reg = <0x00002000 0x1000>;
+			reg = <0x0 0x00002000 0x0 0x1000>;
 			interrupts = <GIC_SPI 259 IRQ_TYPE_LEVEL_HIGH>;
 			phys = <&usbphy0 0>, <&usbphy0 1>;
 			phy-names = "phy0", "phy1";
@@ -38,21 +38,21 @@
 
 		usbphy1: usb-phy@10000 {
 			compatible = "brcm,sr-usb-combo-phy";
-			reg = <0x00010000 0x100>;
+			reg = <0x0 0x00010000 0x0 0x100>;
 			#phy-cells = <1>;
 			status = "disabled";
 		};
 
 		usbphy2: usb-phy@20000 {
 			compatible = "brcm,sr-usb-hs-phy";
-			reg = <0x00020000 0x100>;
+			reg = <0x0 0x00020000 0x0 0x100>;
 			#phy-cells = <0>;
 			status = "disabled";
 		};
 
 		xhci1: usb@11000 {
 			compatible = "generic-xhci";
-			reg = <0x00011000 0x1000>;
+			reg = <0x0 0x00011000 0x0 0x1000>;
 			interrupts = <GIC_SPI 263 IRQ_TYPE_LEVEL_HIGH>;
 			phys = <&usbphy1 1>, <&usbphy2>, <&usbphy1 0>;
 			phy-names = "phy0", "phy1", "phy2";
@@ -62,7 +62,7 @@
 
 		bdc1: usb@21000 {
 			compatible = "brcm,bdc-v0.16";
-			reg = <0x00021000 0x1000>;
+			reg = <0x0 0x00021000 0x0 0x1000>;
 			interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>;
 			phys = <&usbphy2>;
 			phy-names = "phy0";

arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts

@@ -10,18 +10,6 @@
 	model = "NVIDIA Jetson TX2 Developer Kit";
 	compatible = "nvidia,p2771-0000", "nvidia,tegra186";
 
-	aconnect {
-		status = "okay";
-
-		dma-controller@2930000 {
-			status = "okay";
-		};
-
-		interrupt-controller@2a40000 {
-			status = "okay";
-		};
-	};
-
 	i2c@3160000 {
 		power-monitor@42 {
 			compatible = "ti,ina3221";

arch/arm64/boot/dts/rockchip/rk3399.dtsi

@@ -29,6 +29,9 @@
 		i2c6 = &i2c6;
 		i2c7 = &i2c7;
 		i2c8 = &i2c8;
+		mmc0 = &sdio0;
+		mmc1 = &sdmmc;
+		mmc2 = &sdhci;
 		serial0 = &uart0;
 		serial1 = &uart1;
 		serial2 = &uart2;

arch/powerpc/Makefile

@@ -250,7 +250,6 @@ KBUILD_CFLAGS		+= $(call cc-option,-mno-string)
 
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
-cpu-as-$(CONFIG_E200)		+= -Wa,-me200
 cpu-as-$(CONFIG_E500)		+= -Wa,-me500
 
 # When using '-many -mpower4' gas will first try and find a matching power4

arch/powerpc/platforms/powernv/setup.c

@@ -186,11 +186,16 @@ static void __init pnv_init(void)
 		add_preferred_console("hvc", 0, NULL);
 
 	if (!radix_enabled()) {
+		size_t size = sizeof(struct slb_entry) * mmu_slb_size;
 		int i;
 
 		/* Allocate per cpu area to save old slb contents during MCE */
-		for_each_possible_cpu(i)
-			paca_ptrs[i]->mce_faulty_slbs = memblock_alloc_node(mmu_slb_size, __alignof__(*paca_ptrs[i]->mce_faulty_slbs), cpu_to_node(i));
+		for_each_possible_cpu(i) {
+			paca_ptrs[i]->mce_faulty_slbs =
+					memblock_alloc_node(size,
+						__alignof__(struct slb_entry),
+						cpu_to_node(i));
+		}
 	}
 }
 

arch/powerpc/platforms/pseries/msi.c

@@ -458,7 +458,8 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
 			return hwirq;
 		}
 
-		virq = irq_create_mapping(NULL, hwirq);
+		virq = irq_create_mapping_affinity(NULL, hwirq,
+						   entry->affinity);
 
 		if (!virq) {
 			pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq);

arch/x86/include/asm/insn.h

@@ -195,6 +195,21 @@ static inline int insn_offset_immediate(struct insn *insn)
 	return insn_offset_displacement(insn) + insn->displacement.nbytes;
 }
 
+/**
+ * for_each_insn_prefix() -- Iterate prefixes in the instruction
+ * @insn: Pointer to struct insn.
+ * @idx:  Index storage.
+ * @prefix: Prefix byte.
+ *
+ * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix
+ * and the index is stored in @idx (note that this @idx is just for a cursor,
+ * do not change it.)
+ * Since prefixes.nbytes can be bigger than 4 if some prefixes
+ * are repeated, it cannot be used for looping over the prefixes.
+ */
+#define for_each_insn_prefix(insn, idx, prefix)	\
+	for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++)
+
 #define POP_SS_OPCODE 0x1f
 #define MOV_SREG_OPCODE 0x8e
 

arch/x86/include/asm/pgtable_types.h

@@ -147,6 +147,7 @@ enum page_cache_mode {
 #endif
 
 #define _PAGE_CACHE_MASK	(_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)
+#define _PAGE_LARGE_CACHE_MASK	(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT_LARGE)
 #define _PAGE_NOCACHE		(cachemode2protval(_PAGE_CACHE_MODE_UC))
 #define _PAGE_CACHE_WP		(cachemode2protval(_PAGE_CACHE_MODE_WP))
 

arch/x86/include/asm/sync_core.h

@@ -16,12 +16,13 @@ static inline void sync_core_before_usermode(void)
 	/* With PTI, we unconditionally serialize before running user code. */
 	if (static_cpu_has(X86_FEATURE_PTI))
 		return;
+
 	/*
-	 * Return from interrupt and NMI is done through iret, which is core
-	 * serializing.
+	 * Even if we're in an interrupt, we might reschedule before returning,
+	 * in which case we could switch to a different thread in the same mm
+	 * and return using SYSRET or SYSEXIT.  Instead of trying to keep
+	 * track of our need to sync the core, just sync right away.
 	 */
-	if (in_irq() || in_nmi())
-		return;
 	sync_core();
 }
 

arch/x86/kernel/apic/vector.c

@@ -272,20 +272,24 @@ static int assign_irq_vector_any_locked(struct irq_data *irqd)
 	const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd);
 	int node = irq_data_get_node(irqd);
 
-	if (node == NUMA_NO_NODE)
-		goto all;
-	/* Try the intersection of @affmsk and node mask */
-	cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk);
-	if (!assign_vector_locked(irqd, vector_searchmask))
-		return 0;
-	/* Try the node mask */
-	if (!assign_vector_locked(irqd, cpumask_of_node(node)))
-		return 0;
-all:
+	if (node != NUMA_NO_NODE) {
+		/* Try the intersection of @affmsk and node mask */
+		cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk);
+		if (!assign_vector_locked(irqd, vector_searchmask))
+			return 0;
+	}
+
 	/* Try the full affinity mask */
 	cpumask_and(vector_searchmask, affmsk, cpu_online_mask);
 	if (!assign_vector_locked(irqd, vector_searchmask))
 		return 0;
+
+	if (node != NUMA_NO_NODE) {
+		/* Try the node mask */
+		if (!assign_vector_locked(irqd, cpumask_of_node(node)))
+			return 0;
+	}
+
 	/* Try the full online mask */
 	return assign_vector_locked(irqd, cpu_online_mask);
 }

arch/x86/kernel/uprobes.c

@@ -255,12 +255,13 @@ static volatile u32 good_2byte_insns[256 / 32] = {
 
 static bool is_prefix_bad(struct insn *insn)
 {
+	insn_byte_t p;
 	int i;
 
-	for (i = 0; i < insn->prefixes.nbytes; i++) {
+	for_each_insn_prefix(insn, i, p) {
 		insn_attr_t attr;
 
-		attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
+		attr = inat_get_opcode_attribute(p);
 		switch (attr) {
 		case INAT_MAKE_PREFIX(INAT_PFX_ES):
 		case INAT_MAKE_PREFIX(INAT_PFX_CS):
@@ -715,6 +716,7 @@ static const struct uprobe_xol_ops push_xol_ops = {
 static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 {
 	u8 opc1 = OPCODE1(insn);
+	insn_byte_t p;
 	int i;
 
 	switch (opc1) {
@@ -746,8 +748,8 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 	 * Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix.
 	 * No one uses these insns, reject any branch insns with such prefix.
 	 */
-	for (i = 0; i < insn->prefixes.nbytes; i++) {
-		if (insn->prefixes.bytes[i] == 0x66)
+	for_each_insn_prefix(insn, i, p) {
+		if (p == 0x66)
 			return -ENOTSUPP;
 	}
 

arch/x86/lib/insn-eval.c

@@ -70,14 +70,15 @@ static int get_seg_reg_override_idx(struct insn *insn)
 {
 	int idx = INAT_SEG_REG_DEFAULT;
 	int num_overrides = 0, i;
+	insn_byte_t p;
 
 	insn_get_prefixes(insn);
 
 	/* Look for any segment override prefixes. */
-	for (i = 0; i < insn->prefixes.nbytes; i++) {
+	for_each_insn_prefix(insn, i, p) {
 		insn_attr_t attr;
 
-		attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
+		attr = inat_get_opcode_attribute(p);
 		switch (attr) {
 		case INAT_MAKE_PREFIX(INAT_PFX_CS):
 			idx = INAT_SEG_REG_CS;

arch/x86/lib/memcpy_64.S

@@ -15,8 +15,6 @@
  * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
  */
 
-.weak memcpy
-
 /*
  * memcpy - Copy a memory block.
  *
@@ -29,7 +27,7 @@
  * rax original destination
  */
 ENTRY(__memcpy)
-ENTRY(memcpy)
+SYM_FUNC_START_WEAK(memcpy)
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 

arch/x86/lib/memmove_64.S

@@ -24,9 +24,7 @@
  * Output:
  * rax: dest
  */
-.weak memmove
-
-ENTRY(memmove)
+SYM_FUNC_START_WEAK(memmove)
 ENTRY(__memmove)
 
 	/* Handle more 32 bytes in loop */

arch/x86/lib/memset_64.S

@@ -6,8 +6,6 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
-.weak memset
-
 /*
  * ISO C memset - set a memory block to a byte value. This function uses fast
  * string to get better performance than the original function. The code is
@@ -19,7 +17,7 @@
  *
  * rax   original destination
  */
-ENTRY(memset)
+SYM_FUNC_START_WEAK(memset)
 ENTRY(__memset)
 	/*
 	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended